AI-Driven Security: How Machine Learning Will Shape the Future of Cybersecurity and Web 3.0
Issue:
Volume 9, Issue 1, June 2023
Pages:
1-7
Received:
7 May 2023
Accepted:
26 May 2023
Published:
10 June 2023
Abstract: As the world becomes increasingly digital, the need for advanced cybersecurity measures has never been greater. Cybersecurity is the practice of protecting computer systems, networks, and digital information from unauthorized access, theft, or damage. With the increasing reliance on digital technology in almost every aspect of modern life, the importance of cybersecurity has become paramount. The use of internet-connected devices has skyrocketed in recent years, with the number of devices expected to reach 20.4 billion by 2023, according to a report by Gartner. Traditional security methods are no longer sufficient to protect against sophisticated and evolving threats of today. Artificial intelligence (AI) offers a promising solution, with the potential to revolutionize the way we approach cybersecurity. In this paper, we explore the role of machine learning algorithms in security and their ability to automate tasks and reduce false positives. We also discuss the challenges and limitations of AI in security, including the lack of transparency in algorithms and the potential for vulnerability to hacking or manipulation. Looking towards the future, we predict that AI will play an even greater role in security and have a significant impact on Web 3.0 and other areas such as fraud detection and risk management.
Abstract: As the world becomes increasingly digital, the need for advanced cybersecurity measures has never been greater. Cybersecurity is the practice of protecting computer systems, networks, and digital information from unauthorized access, theft, or damage. With the increasing reliance on digital technology in almost every aspect of modern life, the impo...
Show More
Research Article
Modelling and Forecasting Inflation Rates in Kenya Using ARIMA-ANN Hybrid Model
Barry Agingu Jagero,
Thomas Mageto,
Samuel Mwalili
Issue:
Volume 9, Issue 1, June 2023
Pages:
8-17
Received:
27 September 2023
Accepted:
16 October 2023
Published:
28 October 2023
Abstract: This study explored the complexities of modeling and forecasting inflation rates in Kenya, leveraging a sophisticated ARIMA-ANN hybrid model. Traditional ARIMA models, although proficient in capturing linear relationships, often falter in the face of non-linear, complex patterns inherent in economic data. To enhance accuracy, we integrated an ANN with a specifically chosen ARIMA (1, 0, 11) model, benefiting from ANN’s capability to delineate non-linear correlations and intricacies. This hybrid model was meticulously trained to minimize the MSE, epitomizing efficiency in both training and validation phases. Empirical results showcased the model’s commendable predictive accuracy. A comparative analysis accentuated its supremacy over the traditional ARIMA model, delineated by superior MSE, RMSE, MAE, and MAPE metrics. The hybrid model adeptly amalgamated ARIMA’s statistical robustness with ANN’s adeptness at non-linear pattern recognition, ensuring enhanced forecast precision. The model is not just a theoretical construct but a pragmatic tool, instrumental for policymakers, economists, and stakeholders, offering insightful foresights that are pivotal for strategic planning and decision-making. The forecasting accuracy of our hybrid model was rigorously tested against actual inflation data, and its performance metrics underscored reliability and precision. Future research could potentially augment this model by integrating more advanced neural network architectures, and incorporating external economic indicators to further enhance forecasting accuracy. This study is a substantial stride towards a nuanced understanding of inflation dynamics in Kenya, offering tools that are not only statistically robust but also practically applicable in real-world economic scenarios. This intricate blend of statistical and machine learning techniques promises to be a cornerstone for future economic forecasting endeavors.
Abstract: This study explored the complexities of modeling and forecasting inflation rates in Kenya, leveraging a sophisticated ARIMA-ANN hybrid model. Traditional ARIMA models, although proficient in capturing linear relationships, often falter in the face of non-linear, complex patterns inherent in economic data. To enhance accuracy, we integrated an ANN w...
Show More
